AI Operations Agent for a Business Director
One Telegram interface for tasks, finance, knowledge retrieval, calendar, and inbox triage, connected to the systems the company already usesSelf-hosted, and it retains authorized operational context across those systems between conversations
Tasks, finance, knowledge and inbox triage in one interface.
The situation
A director was running the business from memory and a dozen open apps. Notes scattered across chat, email, and paper. Finances reconciled by hand from each bank export. Deadlines and promises to people slipped through, and finding the right past email or document meant a long hunt every time.
How we built it
A self-hosted tool-use orchestrator the director operates from a single Telegram chat. Each request passes through input validation, model routing with a cost gate, knowledge recall, a tool loop, and a supervisor that checks every answer against its sources before it is sent. It integrates with the systems the company already uses, and any destructive action requires explicit confirmation from the user.
What it does
Universal capture
Voice, photo, or text dropped into the chat is transcribed, classified, and routed to the right place: a task, a fact, a contact, an event, a commitment, or the journal.
Task lifecycle
Due-date handling, two-tier de-duplication, auto-snooze with a single reminder, and escalation, so stale and overdue tasks are surfaced automatically rather than sitting unreviewed.
Finance automation
Bank accounts sync automatically; transactions are auto-categorized, with month-end forecasting and bulk-undo for corrections.
Inbox & subscriptions
Email is triaged on a schedule with per-message classification; recurring subscriptions are detected from the inbox and flagged ahead of renewal.
Calendar & commitments
Two-way calendar sync with conflict detection, plus promise tracking that knows what is owed and what is awaited, and expires stale commitments.
Knowledge base & RAG
A hybrid keyword-plus-vector search over hundreds of unified documents (email, drive, voice notes) answers in a second or two, with the source cited.
Memory graph
Entities and facts are extracted into a graph with entity resolution, so the assistant remembers people, deals, and decisions across conversations.
Governance & safety
Explicit user approval for destructive, high-cost, or bulk actions; an encrypted private journal; and dashboards for answer quality and per-operation cost, with configured limits.
Technical scale
- 21
- Functional modules
- ~95
- LLM tools
- 14
- External integrations
- 8
- Background daemons
- 49
- Database migrations
- 289
- Documents indexed
What it runs on
AI core
Claude Sonnet 4.6 / Opus 4.7, GPT-4o and GPT-4o-mini, Haiku 4.5, Gemini fallback, text-embedding-3-small
Voice & input
gpt-4o-transcribe, an ffmpeg clean-up pipeline for noisy audio, Telegram Bot API, web speech
Storage
PostgreSQL with pgvector and pg_trgm, row-level security across per-agent roles, column-level AES-GCM encryption
Backend
Python and FastAPI, async Postgres, a tool-use orchestrator running skills in-process
Frontend
React and TypeScript dashboard with a live memory graph, charts, and a quality view
Infrastructure
Single self-hosted VM, Docker Compose, least-privilege service user, no vendor lock-in
A deeper breakdown of the architecture and modules is available on request. There is too much detail for a public page.
What changed
- Retrieving a past email or document became a one-to-two-second search returning the source document.
- Roughly 97% of transactions are categorized automatically, where categorization used to be entirely manual.
- Detected subscription renewals are flagged about a week before the charge date.
- Eight background processes run on schedule without manual triggers.
- One Telegram interface replaced switching between separate apps for tasks, finance, mail and calendar.
- Per-operation cost is recorded, and configured limits prevent uncontrolled model spend.